arXiv subjects

Linh Ngo

Publications and source records attributed to Linh Ngo.

4 recordsLinked to original sources

arXiv2025

Few-shot Continual Relation Extraction via Open Information Extraction

Typically, Few-shot Continual Relation Extraction (FCRE) models must balance retaining prior knowledge while adapting to new tasks with extremely limited data. However, real-world scenarios may also involve unseen or undetermined relations that existing methods still struggle to handle. To address these challenges, we propose a novel approach that leverages the Open Information Extraction concept of Knowledge Graph Construction (KGC). Our method not only exposes models to all possible pairs of relations, including determined and undetermined labels not available in the training set, but also enriches model knowledge with diverse relation descriptions, thereby enhancing knowledge retention and adaptability in this challenging scenario. In the perspective of KGC, this is the first work explored in the setting of Continual Learning, allowing efficient expansion of the graph as the data evolves. Experimental results demonstrate our superior performance compared to other state-of-the-art FCRE baselines, as well as the efficiency in handling dynamic graph construction in this setting.

cs.LG↗

arXiv2024

Leveraging Hierarchical Taxonomies in Prompt-based Continual Learning

Humans perceive the world as a series of sequential events, which can be hierarchically organized with different levels of abstraction based on conceptual knowledge. Drawing inspiration from human learning behaviors, this work proposes a novel approach to mitigate catastrophic forgetting in Prompt-based Continual Learning models by exploiting the relationships between continuously emerging class data. We find that applying human habits of organizing and connecting information can serve as an efficient strategy when training deep learning models. Specifically, by building a hierarchical tree structure based on the expanding set of labels, we gain fresh insights into the data, identifying groups of similar classes could easily cause confusion. Additionally, we delve deeper into the hidden connections between classes by exploring the original pretrained model's behavior through an optimal transport-based approach. From these insights, we propose a novel regularization loss function that encourages models to focus more on challenging knowledge areas, thereby enhancing overall performance. Experimentally, our method demonstrated significant superiority over the most robust state-of-the-art models on various benchmarks.

cs.LG↗

arXiv2022

An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning

In online incremental learning, data continuously arrives with substantial distributional shifts, creating a significant challenge because previous samples have limited replay value when learning a new task. Prior research has typically relied on either a single adaptive centroid or multiple fixed centroids to represent each class in the latent space. However, such methods struggle when class data streams are inherently multimodal and require continual centroid updates. To overcome this, we introduce an online Mixture Model learning framework grounded in Optimal Transport theory (MMOT), where centroids evolve incrementally with new data. This approach offers two main advantages: (i) it provides a more precise characterization of complex data streams, and (ii) it enables improved class similarity estimation for unseen samples during inference through MMOT-derived centroids. Furthermore, to strengthen representation learning and mitigate catastrophic forgetting, we design a Dynamic Preservation strategy that regulates the latent space and maintains class separability over time. Experimental evaluations on benchmark datasets confirm the superior effectiveness of our proposed method.

cs.LG↗

arXiv2017

A 1574-day periodicity of transits orbiting KIC 8462852

Observations of the main sequence F3 V star KIC 8462852 (also known as Boyajian's star) revealed extreme aperiodic dips in flux up to 20% during the four years of the Kepler mission. Smaller dips (< 2%) were also observed with ground-based telescopes between May and September 2017. We investigated possible correlation between recent dips and the major dips in the last 100 days of the Kepler mission. We compared Kepler light curve data, 2017 data from two observatories (TFN, OGG) which are part of the Las Cumbres Observatory (LCO) network and Sternberg observatory archival data, and determined that observations are consistent with a 1,574-day (4.31 year) periodicity of a transit (or group of transits) orbiting Boyajian's star within the habitable zone. It is unknown if transits that have produced other major dips as observed during the Kepler mission (e.g. D792) share the same orbital period. Nevertheless, the proposed periodicity is a step forward in guiding future observation efforts.

astro-ph.SR↗